检索结果-内蒙古大学图书馆

IEEE International Conference on engineering Technologies and Applied Sciences (ICETAS)

作者： Nivine Guler Ali Gunes Department of Informatics Engineering University of Technology Bahrain Kingdom of Bahrain Department of Computer Engineering Istanbul Aydin University Turkey

In this paper, an efficient resource allocation scheme-based nonlinear energy harvesting (EH) Timeslot switching (TS) for single-input-single-output (SISO) SWIPT systems-(ERAS-NETS) is presented. The energy saturation characteristic is considered in the EH model where point-to-point (P2P) single-input single-output (P2P-SISO) SWIPT system is studied. Harvesting energy is based on Timeslot switching (TS) aiming at optimizing the average data rate where the TS ratio is a binary value (0 or 1). Hence, the problem is a nonconvex optimization problem because of the binary factor of the TS ratio. The optimization problem is solved using the Lagrange dual theorem that states that the optimal values of the Primal (P) and Dual (D) linear problem are the same if either solution is a basic feasible solution. Accordingly, the derivation of the optimal solution helps receiver to switch either to EH or information decoding (ID) based on the SNR value. Hence, the receiver will switch to EH in the districts having medium values of SNR, otherwise, the receiver will switch to ID in districts having SNR less than 5 dB or more than 25 dB. Different network performance metrics were considered in evaluating the proposed ERAS-NETS scheme in comparison with traditional state-in-the-art TS resource allocation schemes such as transmission power, distance between source and destination, pathloss exponent, and minimum required harvested energy. Simulations showed that ERAS-NETS improves energy efficiency with respect to different transmission power by 20%, 10%, and 3 % for high SNR, medium SNR, and low SNR districts, respectively. Improvement with respect to average energy efficiency versus other system performance metrics has also been noted for the proposed scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Peer to Peer Federated Learning: Towards Decentralized Machine Learning on Edge Devices 7

Peer to Peer Federated Learning: Towards Decentralized Machi...

引用

7th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2022

作者： Karras, Aristeidis Karras, Christos Giotopoulos, Konstantinos C. Tsolis, Dimitrios Oikonomou, Konstantinos Sioutas, Spyros University of Patras Decentralized Systems Computing Group Computer Engineering and Informatics Department Patras Greece University of Patras Department of Management Science and Technology Patras Greece Ionian University Department of Informatics Corfu Greece

ISBN: (数字)9798350398588

ISBN: (纸本)9798350398588

Federated Learning (FL) is an emerging technique that assures user privacy and data integrity in distributed machine learning environments. To perform so, chunks of data are trained across edge devices and a high performance cluster server maintains a local copy without exchanging it with other parties. In this work, we investigate a FL scenario in a real-world case study using 5, 10 and 20 Raspberry Pi devices acting as clients. Under this setup, we employ the widely known FedAvg algorithm which trains each client for several local epochs and then the weight of each model is aggregated. Moreover we perform experiments across imbalanced and noisy data so as to explore scalability and robustness based on real-world datasets were noise is present and we also propose two innovative algorithms where the FL scenario is considered as a peer-to-peer formulation. Ultimately, to ensure that each device is not oversampled a client-balancing Dirichlet sampling algorithm with probabilistic guarantees is proposed. © 2022 IEEE.

关键词： computer aided instruction

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multidimensional Harmonic Retrieval in MIMO Wireless Channel Sounding

引用

IEEE Internet of Things Journal 2025年第11期12卷 16243-16255页

作者： Zhang, Yanming Xu, Wenchao Jin, A-Long Tang, Tianquan Li, Min Ma, Peifeng Jiang, Lijun Gao, Steven The Chinese University of Hong Kong Department of Electronic Engineering Hong Kong Hong Kong The Hong Kong Polytechnic University Department of Computing Hong Kong Xi’an Jiaotong-Liverpool University Department of Communications and Networking Suzhou215123 China HKU Zhejiang Institute of Research and Innovation Lab for Aerodynamics and Acoustics Hangzhou311305 China Tianjin University School of Microelectronics Tianjin300000 China Institute of Space and Earth Information Science The Chinese University of Hong Kong Department of Geography and Resource Management Hong Kong Missouri University of Science and Technology Department of Electrical and Computer Engineering RollaMO65409 United States

This article introduces a recursive parallel dynamic mode decomposition (RPDMD) scheme tailored for multidimensional harmonic retrieval (MHR), specifically applied to MIMO wireless channel sounding. The RPDMD algorithm is devised to address the complexities inherent in multidimensional scenarios, leveraging the dynamic mode decomposition (DMD) framework within a recursive parallel structure. Initially, the observed tensorial multidimensional harmonic data is transformed into a 2-D matrix format along the rth dimension. Subsequently, DMD dissects this matrix data into eigenvalues and their associated modes. The real and imaginary components of the DMD eigenvalues yield damping factors and frequencies in the rth dimension, respectively. Furthermore, recursive DMD is employed to scrutinize each mode independently for parameter retrieval across the remaining dimensions, enabling parallel analysis. Ultimately, this high-dimensional correlated decomposition scheme delivers paired damping factors and frequencies for all tones. Notably, the proposed approach can ascertain the number of tones in undamped sinusoidal signals, making it particularly suitable for MHR even without prior knowledge of the source count. Numerical experiments demonstrate the accuracy and robustness of the RPDMD scheme, with comparative analysis indicating that RPDMD outperforms similar methods, achieving optimal results with minimal mean square error in high signal-to-noise ratio scenarios. This work presents an effective data-driven solution for the MHR problem in MIMO wireless channel sounding. © 2014 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Detecting Retinal Nerve Fiber Layer Using Gray Level Co-occurrence Matrix and Machine Learning Approach

Detecting Retinal Nerve Fiber Layer Using Gray Level Co-occu...

引用

2022 International Conference on Information Technology Research and Innovation, ICITRI 2022

作者： Septiarini, Anindita Hamdani, Hamdani Setyaningsih, Emy Maharani, Septya Munir, Aam Shodiqul Winarno, Edy Mulawarman University Faculty of Engineering Department of Informatics Samarinda Indonesia Institut Sains Teknologi AKPRIND Department of Computer System Engineering Yogyakarta Indonesia Universitas Stikubank Faculty of Information Technology Semarang Indonesia

ISBN: (数字)9781665461849

ISBN: (纸本)9781665461849

The retinal nerve fiber layer (RNFL) is the white scratch part in the fundus image. It could be an indicator of several diseases characterized by depletion of RNFL. This study intends to construct an RNFL method using Gray Level Cooccurrence Matrix (GLCM) as texture features and implementing random forest as the classifier. The approach has four primary steps: defining the region of interest (ROI), forming the area of features extraction, pre-processing, feature extraction, and classification. Forming the ROI was applied through two main steps: The segmentation with K-means clustering and dividing the fundus image into 12 sub-sectors. The image was then turned into a grayscale as part of the pre-processing. Afterward, the features were extracted using GLCM, followed by features reduction with Correlation-based Feature Selection (CFS). The last step was to use the artificial neural network (ANN) method to classify the data. In this study, the RNFL detection method achieved the accuracy value of 96.7% against the dataset consisting of 40 images. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Live Video Streaming for Object Detection 23

Intelligent Live Video Streaming for Object Detection

引用

23rd IEEE International Conference on High Performance Computing and Communications, 7th IEEE International Conference on Data Science and Systems, 19th IEEE International Conference on Smart City and 7th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Chen, Mingkang Sun, Jingtao Aida, Kento Figueiredo, Renato J. Ku, Yun-Jung Subratie, Kensworth The Graduate University for Advanced Studies Sokendai Department of Informatics Tokyo Japan National Institute of Informatics Tokyo Japan University of Florida Electrical and Computer Engineering Florida United States

ISBN: (纸本)9781665494571

These days, sensors and cameras are being deployed on an increasingly large scale. Furthermore, the rapid development of machine learning models for computer vision now presents novel opportunities for the use of artificial intelligence (AI) and Internet of Things (IoT) combinations in various application scenarios. However, challenges remain in supporting low-latency video streaming from distributed mobile IoT devices under dynamic network environments, and overcoming video data quality degradation that results from weather 'noise', which reduces the accuracy of AI-based data analyses such as object detection. In this paper, we propose a live video stream processing system for supporting intelligent services that integrates the following features. First, to cope with dynamic networks and achieve low latency, our approach employs a peer-to-peer (P2P)-based virtual network at the edge and a multi-tiered architecture composed of IoT cameras, edge, and cloud servers. Second, we construct a flexible messaging system for video analysis built upon SINETStream, which is a messaging system that adopts a topic-based pub/sub model. Third, we implement a framework that can remove weather-related (rain, snow, and fog) noise by applying weather classification and adaptive noise removal models that improve the accuracy of video analysis from data collected outdoors. The latency, throughput, and image quality benchmark experiments conducted to validate the feasibility of our proposed system showed that the process resulted in image quality improvements of approximately 30% (on average). © 2021 IEEE.

关键词： Image quality Adaptation models Image edge detection Object detection Streaming media Throughput Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Facilitating Knowledge Transfer: An Approach for Matching Neural Patterns between Motor Tasks

Facilitating Knowledge Transfer: An Approach for Matching Ne...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Zhiwei Song Xiang Zhang Jieyuan Tan Mingyi Wang Yiwen Wang Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Chemical and Biological Engineering Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Brain-machine interface (BMI) holds great promise for restoring the impaired motor functions of individuals. In real-life scenarios, BMI users often face the challenge of quickly learning new tasks to adapt to complex environments. Consequently, it becomes essential to investigate the transferability of knowledge (neural-action mapping) of the decoder gained from previously learned tasks to new tasks. This paper introduces an approach for matching neural patterns between motor tasks to facilitate knowledge transfer, which is a key step in facilitating knowledge transfer. We project neural data into a 6D jPCA feature space and observe that neural patterns associated with the same action are preserved in the last four dimensions. By utilizing the decoder trained from the previous task, we obtain a prior estimate of the matched class. This prior estimate is further refined by clustering the neural patterns in the first two dimensions, as the data demonstrates distinct cluster shapes. To validate our approach, we conducted an experiment where a rat learned two related motor tasks sequentially. The preliminary results showed that our proposed method achieved an accuracy of 87.04% in estimating the matched class compared to the ground truth. In contrast, utilizing the decoder trained from the previous task within the entire jPCA space resulted in a significantly lower accuracy of merely 39.8%. These findings highlight the efficacy of our proposed method in matching neural patterns between motor tasks, thus facilitating knowledge transfer.

关键词： Knowledge engineering Accuracy Shape Rats Motors Decoding engineering in medicine and biology Pattern matching Knowledge transfer Faces

来源：评论

学校读者我要写书评

暂无评论

Increasing Reliability in Hybrid RF-Optical Networks: A Cross-Band Modulation Design

Increasing Reliability in Hybrid RF-Optical Networks: A Cros...

引用

IEEE Conference on Wireless Communications and Networking

作者： Thrassos K. Oikonomou Sotiris A. Tegos Panagiotis D. Diamantoulakis Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Department of Applied Informatics University of Macedonia Thessaloniki Greece

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

This paper presents a novel hybrid cross-band radio frequency (RF)-optical system that utilizes coherent RF detection with $M$ -QAM modulation and optical intensity modulation and direct detection (IM/DD) to fully utilize the diversity gains of cross-band architectures. By performing joint signal processing in the RF and optical domains, the proposed system achieves significant improvements in reliability, spectral efficiency, and data rates compared to conventional approaches. A key feature of the system is an optimized linear mapping between the RF and optical signals, which ensures seamless signal integration and improved performance. To evaluate the system, we derive the theoretical mutual information (MI) and a tight closed-form approximation for the symbol error probability (SEP) of the proposed modulation scheme. Numerical results validate the theoretical analysis and show that the proposed scheme significantly outperforms state-of-the-art cross-band modulations in terms of MI and SEP. The proposed scheme, with its low-complexity design and superior performance, is a promising candidate for next-generation wireless networks.

关键词： Radio frequency Error probability Spectral efficiency Wireless networks Symbols Reliability theory Optical receivers Adaptive optics Optical signal processing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Freeplane: Unlocking Free Lunch in Triplane-Based Sparse-View Reconstruction Models

arXiv

引用

arXiv 2024年

作者： Sun, Wenqiang Wang, Zhengyi Chen, Shuo Wang, Yikai Chen, Zilong Zhu, Jun Zhang, Jun Department of Electronic and Computer Engineering HKUST Hong Kong Department of Computer Science and Technology Tsinghua University China ShengShu China

Creating 3D assets from single-view images is a complex task that demands a deep understanding of the world. Recently, feed-forward 3D generative models have made significant progress by training large reconstruction models on extensive 3D datasets, with triplanes being the preferred 3D geometry representation. However, effectively utilizing the geometric priors of triplanes, while minimizing artifacts caused by generated inconsistent multi-view images, remains a challenge. In this work, we present Frequency modulated triplane (Freeplane), a simple yet effective method to improve the generation quality of feed-forward models without additional training. We first analyze the role of triplanes in feed-forward methods and find that the inconsistent multi-view images introduce high-frequency artifacts on triplanes, leading to low-quality 3D meshes. Based on this observation, we propose strategically filtering triplane features and combining triplanes before and after filtering to produce high-quality textured meshes. These techniques incur no additional cost and can be seamlessly integrated into pre-trained feed-forward models to enhance their robustness against the inconsistency of generated multi-view images. Both qualitative and quantitative results demonstrate that our method improves the performance of feed-forward models by simply modulating triplanes. All you need is to modulate the triplanes during inference. Copyright © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Employing Deep Neural Networks for Real-Time Anomaly Detection and Mitigation in IoT-Based Smart Grid Cybersecurity Systems 3

Employing Deep Neural Networks for Real-Time Anomaly Detecti...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and electronics, ICDCECE 2024

作者： Quraishi, Aadam Rusho, Maher Ali Prasad, Anurag Keshta, Ismail Rivera, Richard Bhatt, Mohammed Wasim Intervention Treatment Institute Research HoustonTX United States University Of Colorado Boulder Department Of Lockheed Martin Engineering Management BoulderCO United States Gurugram India College Of Applied Sciences AlMaarefa University Computer Science And Information Systems Department Riyadh Saudi Arabia Escuela Politécnica Nacional Department Of Informatics And Computer Science Quito Ecuador Model Institute Of Engineering And Technology J&K Jammu India

ISBN: (纸本)9798350318609

This research introduces a novel anomaly detection framework for IoT -based Smart Grid Cybersecurity Systems. Leveraging autoencoders, LSTM networks, GANs, SOMs, and transfer learning, our approach achieves superior precision, recall, and execution time compared to existing methods. Visualizations and an ablation study further validate the method's efficiency, emphasizing the critical roles of attention mechanisms and transfer learning. This comprehensive solution addresses the dynamic challenges of smart grid cybersecurity, offering a versatile and adaptive anomaly detection mechanism for real-world applications. This indicates the real-time efficacy of our anomaly detection method. Through our study of ablation and all aspects of computing, we discovered that attention processes and transfer learning facilitate faster problem solving in a dynamic smart grid. Our method is distinct and adaptable enough to address every problem arising from the discovery of anomalies in IoT-driven Smart Grid Cybersecurity Systems. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Hysteresis Current Control of Single-Phase Single-Stage Grid-Connected Inverter with Buck-Boost Operation Capability 49

Hysteresis Current Control of Single-Phase Single-Stage Grid...

引用

49th Annual Conference of the IEEE Industrial electronics Society, IECON 2023

作者： Komurcugil, Hasan Guler, Naki Bayhan, Sertac Guzman, Ramon Eastern Mediterranean University Department of Computer Engineering Famagusta Turkey Gazi University Technology Faculty Department of Electrical-Electronic Engineering Ankara Turkey Qatar Environment and Energy Research Institute Hamad Bin Khalifa University Doha Qatar Technical University of Catalonia Spain

ISBN: (纸本)9798350331820

This paper presents a hysteresis current control for single-phase single-stage buck-boost grid-connected inverters. The inverter topology employs four switches that are operated with the grid frequency and two bidirectional switches that are operated with high switching frequency. Hence, unlike the existing single-stage inverter topologies, the switching losses are minimized. Moreover, this inverter configuration has the capability to operate both in buck and boost modes and utilizes only a single inductor. The proposed hysteresis current control eliminates the need for designing a dedicated modulation technique for this inverter topology. An active damping technique is utilized to cope with the resonance damping problem without employing additional sensor. The reference current needed in the hysteresis controller is produced using a proportional-resonant (PR) controller whose input is the grid current error. The use of PR controller guarantees zero steady-state error in the grid current. The validity and superiority of the proposed control method are confirmed by MATLAB/Simulink simulations under various operating conditions which include buck mode, boost mode, transition from boost mode to buck mode, reference current change and virtual resistor variation. The simulation results show that the proposed control method is able to transfer the desired current into grid successfully under all operating conditions. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：